Efficient And Scalable Neural Residual Waveform Coding With Collaborative Quantization

Abstract

Scalability and efficiency are desired in neural speech codecs, which supports a wide range of bitrates for applications on various devices. We propose a collaborative quantization (CQ) scheme to jointly learn the codebook of LPC coefficients and the corresponding residuals. CQ does not simply shoehorn LPC to a neural network, but bridges the computational capacity of advanced neural network models and traditional, yet efficient and domain-specific digital signal processing methods in an integrated manner. We demonstrate that CQ achieves much higher quality than its predecessor at 9 kbps with even lower model complexity. We also show that CQ can scale up to 24 kbps where it outperforms AMR-WB and Opus. As a neural waveform codec, CQ models are with less than 1 million parameters, significantly less than many other generative models.

Stats

• citations13
• S2 citations—
• github stars0
• HF likes0
• heat score8.60
• arxiv keyzhen2020efficient

Related papers

• CQNV: A Combination Of Coarsely Quantized Bitstream And Neural Vocoder For Low Rate Speech Coding (2023)6.34
• Optimizing Neural Speech Codec For Low-bitrate Compression Via Multi-scale Encoding (2024)0.00
• ERVQ: Enhanced Residual Vector Quantization With Intra-and-inter-codebook Optimization For Neural Audio Codecs (2024)6.34
• Variable Bitrate Residual Vector Quantization For Audio Coding (2024)3.58
• Neural Feature Predictor And Discriminative Residual Coding For Low-bitrate Speech Coding (2022)6.77
• Neural Speech Coding For Real-time Communications Using Constant Bitrate Scalar Quantization (2024)0.00
• On The Relation Between Speech Quality And Quantized Latent Representations Of Neural Codecs (2025)0.00
• ESC: Efficient Speech Coding With Cross-scale Residual Vector Quantized Transformers (2024)5.84